© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117154
    Prev
    Next
    INDEX
    Explanations

    webhooks and events

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects tokens that contain numerical digits (i.e. number‐like strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owulf
    -0.91
    دواج
    -0.91
    Tangent
    -0.83
     sommet
    -0.82
     vainqueur
    -0.78
    दो
    -0.78
    Layers
    -0.77
    harapkan
    -0.74
     imbib
    -0.74
     CULTURE
    -0.73
    POSITIVE LOGITS
     webhook
    1.33
    hook
    1.27
     hook
    1.24
    webhook
    1.16
     Web
    1.12
     Hook
    1.10
    Webhook
    0.99
    HOOK
    0.97
    hooks
    0.97
     callback
    0.96
    Activations Density 0.044%

    No Known Activations